mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
5458a88464
* add coverage calculation and push Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * new codecov version and usage of token Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * enable ruff formatter instead of black and isort Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * apply ruff lint fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * apply ruff unsafe fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add removed imports Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * runs 1 on linter issues Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * finalize linter fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Update pyproject.toml Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
78 lines
2.2 KiB
Python
78 lines
2.2 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
from docling_core.types.doc import BoundingBox
|
|
|
|
from docling.backend.docling_parse_backend import (
|
|
DoclingParseDocumentBackend,
|
|
DoclingParsePageBackend,
|
|
)
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.document import InputDocument
|
|
|
|
|
|
@pytest.fixture
|
|
def test_doc_path():
|
|
return Path("./tests/data/pdf/2206.01062.pdf")
|
|
|
|
|
|
def _get_backend(pdf_doc):
|
|
in_doc = InputDocument(
|
|
path_or_stream=pdf_doc,
|
|
format=InputFormat.PDF,
|
|
backend=DoclingParseDocumentBackend,
|
|
)
|
|
|
|
doc_backend = in_doc._backend
|
|
return doc_backend
|
|
|
|
|
|
def test_text_cell_counts():
|
|
pdf_doc = Path("./tests/data/pdf/redp5110_sampled.pdf")
|
|
|
|
doc_backend = _get_backend(pdf_doc)
|
|
|
|
for page_index in range(doc_backend.page_count()):
|
|
last_cell_count = None
|
|
for i in range(10):
|
|
page_backend: DoclingParsePageBackend = doc_backend.load_page(0)
|
|
cells = list(page_backend.get_text_cells())
|
|
|
|
if last_cell_count is None:
|
|
last_cell_count = len(cells)
|
|
|
|
if len(cells) != last_cell_count:
|
|
assert False, (
|
|
"Loading page multiple times yielded non-identical text cell counts"
|
|
)
|
|
last_cell_count = len(cells)
|
|
|
|
|
|
def test_get_text_from_rect(test_doc_path):
|
|
doc_backend = _get_backend(test_doc_path)
|
|
page_backend: DoclingParsePageBackend = doc_backend.load_page(0)
|
|
|
|
# Get the title text of the DocLayNet paper
|
|
textpiece = page_backend.get_text_in_rect(
|
|
bbox=BoundingBox(l=102, t=77, r=511, b=124)
|
|
)
|
|
ref = "DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis"
|
|
|
|
assert textpiece.strip() == ref
|
|
|
|
|
|
def test_crop_page_image(test_doc_path):
|
|
doc_backend = _get_backend(test_doc_path)
|
|
page_backend: DoclingParsePageBackend = doc_backend.load_page(0)
|
|
|
|
# Crop out "Figure 1" from the DocLayNet paper
|
|
page_backend.get_page_image(
|
|
scale=2, cropbox=BoundingBox(l=317, t=246, r=574, b=527)
|
|
)
|
|
# im.show()
|
|
|
|
|
|
def test_num_pages(test_doc_path):
|
|
doc_backend = _get_backend(test_doc_path)
|
|
doc_backend.page_count() == 9
|